models/xgboost-with-estimators.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "9c7c8584",
   "metadata": {},
   "source": [
    "## Data loading"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "ac4b7373",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-01-06T14:13:36.942595Z",
     "iopub.status.busy": "2022-01-06T14:13:36.940840Z",
     "iopub.status.idle": "2022-01-06T14:13:36.962235Z",
     "shell.execute_reply": "2022-01-06T14:13:36.961665Z",
     "shell.execute_reply.started": "2022-01-06T12:53:20.680410Z"
    },
    "papermill": {
     "duration": 0.037487,
     "end_time": "2022-01-06T14:13:36.962372",
     "exception": false,
     "start_time": "2022-01-06T14:13:36.924885",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/kaggle/input/g-research-crypto-forecasting/example_sample_submission.csv\n",
      "/kaggle/input/g-research-crypto-forecasting/asset_details.csv\n",
      "/kaggle/input/g-research-crypto-forecasting/example_test.csv\n",
      "/kaggle/input/g-research-crypto-forecasting/train.csv\n",
      "/kaggle/input/g-research-crypto-forecasting/supplemental_train.csv\n",
      "/kaggle/input/g-research-crypto-forecasting/gresearch_crypto/competition.cpython-37m-x86_64-linux-gnu.so\n",
      "/kaggle/input/g-research-crypto-forecasting/gresearch_crypto/__init__.py\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "import os\n",
    "for dirname, _, filenames in os.walk('/kaggle/input'):\n",
    "    for filename in filenames:\n",
    "        print(os.path.join(dirname, filename))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "c7677b4e",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-01-06T14:13:36.988088Z",
     "iopub.status.busy": "2022-01-06T14:13:36.987484Z",
     "iopub.status.idle": "2022-01-06T14:13:37.954369Z",
     "shell.execute_reply": "2022-01-06T14:13:37.953280Z",
     "shell.execute_reply.started": "2022-01-06T12:53:20.723983Z"
    },
    "papermill": {
     "duration": 0.980975,
     "end_time": "2022-01-06T14:13:37.954507",
     "exception": false,
     "start_time": "2022-01-06T14:13:36.973532",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import gresearch_crypto\n",
    "import warnings\n",
    "import time\n",
    "import traceback\n",
    "import xgboost as xgb\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "dfb2abb8",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-01-06T14:13:37.979137Z",
     "iopub.status.busy": "2022-01-06T14:13:37.978414Z",
     "iopub.status.idle": "2022-01-06T14:13:37.981063Z",
     "shell.execute_reply": "2022-01-06T14:13:37.980622Z",
     "shell.execute_reply.started": "2022-01-06T12:53:21.778297Z"
    },
    "papermill": {
     "duration": 0.01627,
     "end_time": "2022-01-06T14:13:37.981174",
     "exception": false,
     "start_time": "2022-01-06T14:13:37.964904",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "data_train = '/kaggle/input/g-research-crypto-forecasting/train.csv'\n",
    "data_asset_details = '/kaggle/input/g-research-crypto-forecasting/asset_details.csv'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "aa2e4955",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-01-06T14:13:38.006401Z",
     "iopub.status.busy": "2022-01-06T14:13:38.005854Z",
     "iopub.status.idle": "2022-01-06T14:14:30.518925Z",
     "shell.execute_reply": "2022-01-06T14:14:30.518498Z",
     "shell.execute_reply.started": "2022-01-06T12:53:21.789551Z"
    },
    "papermill": {
     "duration": 52.527861,
     "end_time": "2022-01-06T14:14:30.519067",
     "exception": false,
     "start_time": "2022-01-06T14:13:37.991206",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 31.1 s, sys: 2.53 s, total: 33.6 s\n",
      "Wall time: 52.5 s\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>timestamp</th>\n",
       "      <th>Asset_ID</th>\n",
       "      <th>Count</th>\n",
       "      <th>Open</th>\n",
       "      <th>High</th>\n",
       "      <th>Low</th>\n",
       "      <th>Close</th>\n",
       "      <th>Volume</th>\n",
       "      <th>VWAP</th>\n",
       "      <th>Target</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1514764860</td>\n",
       "      <td>2</td>\n",
       "      <td>40</td>\n",
       "      <td>2376.5800</td>\n",
       "      <td>2399.5000</td>\n",
       "      <td>2357.1400</td>\n",
       "      <td>2374.5900</td>\n",
       "      <td>19.233005</td>\n",
       "      <td>2373.116392</td>\n",
       "      <td>-0.004218</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1514764860</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>8.5300</td>\n",
       "      <td>8.5300</td>\n",
       "      <td>8.5300</td>\n",
       "      <td>8.5300</td>\n",
       "      <td>78.380000</td>\n",
       "      <td>8.530000</td>\n",
       "      <td>-0.014399</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1514764860</td>\n",
       "      <td>1</td>\n",
       "      <td>229</td>\n",
       "      <td>13835.1940</td>\n",
       "      <td>14013.8000</td>\n",
       "      <td>13666.1100</td>\n",
       "      <td>13850.1760</td>\n",
       "      <td>31.550062</td>\n",
       "      <td>13827.062093</td>\n",
       "      <td>-0.014643</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1514764860</td>\n",
       "      <td>5</td>\n",
       "      <td>32</td>\n",
       "      <td>7.6596</td>\n",
       "      <td>7.6596</td>\n",
       "      <td>7.6567</td>\n",
       "      <td>7.6576</td>\n",
       "      <td>6626.713370</td>\n",
       "      <td>7.657713</td>\n",
       "      <td>-0.013922</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1514764860</td>\n",
       "      <td>7</td>\n",
       "      <td>5</td>\n",
       "      <td>25.9200</td>\n",
       "      <td>25.9200</td>\n",
       "      <td>25.8740</td>\n",
       "      <td>25.8770</td>\n",
       "      <td>121.087310</td>\n",
       "      <td>25.891363</td>\n",
       "      <td>-0.008264</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    timestamp  Asset_ID  Count        Open        High         Low  \\\n",
       "0  1514764860         2     40   2376.5800   2399.5000   2357.1400   \n",
       "1  1514764860         0      5      8.5300      8.5300      8.5300   \n",
       "2  1514764860         1    229  13835.1940  14013.8000  13666.1100   \n",
       "3  1514764860         5     32      7.6596      7.6596      7.6567   \n",
       "4  1514764860         7      5     25.9200     25.9200     25.8740   \n",
       "\n",
       "        Close       Volume          VWAP    Target  \n",
       "0   2374.5900    19.233005   2373.116392 -0.004218  \n",
       "1      8.5300    78.380000      8.530000 -0.014399  \n",
       "2  13850.1760    31.550062  13827.062093 -0.014643  \n",
       "3      7.6576  6626.713370      7.657713 -0.013922  \n",
       "4     25.8770   121.087310     25.891363 -0.008264  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%%time\n",
    "df_train = pd.read_csv(data_train, \n",
    "                       dtype={'Asset_ID': 'int8', 'Count': 'int32', 'row_id': 'int32', 'Count': 'int32', \n",
    "                              'Open': 'float64', 'High': 'float64', 'Low': 'float64', 'Close': 'float64', \n",
    "                              'Volume': 'float64', 'VWAP': 'float64'\n",
    "                             }\n",
    "                      )\n",
    "df_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "dc97a19b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-01-06T14:14:30.544137Z",
     "iopub.status.busy": "2022-01-06T14:14:30.543575Z",
     "iopub.status.idle": "2022-01-06T14:14:30.562300Z",
     "shell.execute_reply": "2022-01-06T14:14:30.562718Z",
     "shell.execute_reply.started": "2022-01-06T12:54:15.494436Z"
    },
    "papermill": {
     "duration": 0.033256,
     "end_time": "2022-01-06T14:14:30.562860",
     "exception": false,
     "start_time": "2022-01-06T14:14:30.529604",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Asset_ID</th>\n",
       "      <th>Weight</th>\n",
       "      <th>Asset_Name</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>4.304065</td>\n",
       "      <td>Binance Coin</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>6.779922</td>\n",
       "      <td>Bitcoin</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2</td>\n",
       "      <td>2.397895</td>\n",
       "      <td>Bitcoin Cash</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>3</td>\n",
       "      <td>4.406719</td>\n",
       "      <td>Cardano</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>4</td>\n",
       "      <td>3.555348</td>\n",
       "      <td>Dogecoin</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Asset_ID    Weight    Asset_Name\n",
       "1          0  4.304065  Binance Coin\n",
       "2          1  6.779922       Bitcoin\n",
       "0          2  2.397895  Bitcoin Cash\n",
       "10         3  4.406719       Cardano\n",
       "13         4  3.555348      Dogecoin"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_assets = pd.read_csv(data_asset_details).sort_values(by='Asset_ID')\n",
    "df_assets.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "043a862f",
   "metadata": {},
   "source": [
    "## Data preprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "9366badb",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-01-06T14:14:30.592479Z",
     "iopub.status.busy": "2022-01-06T14:14:30.591926Z",
     "iopub.status.idle": "2022-01-06T14:14:30.595606Z",
     "shell.execute_reply": "2022-01-06T14:14:30.595177Z",
     "shell.execute_reply.started": "2022-01-06T12:54:15.519185Z"
    },
    "papermill": {
     "duration": 0.021146,
     "end_time": "2022-01-06T14:14:30.595710",
     "exception": false,
     "start_time": "2022-01-06T14:14:30.574564",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "def upper_shadow(df):\n",
    "    return df['High'] - np.maximum(df['Close'], df['Open'])\n",
    "\n",
    "def lower_shadow(df):\n",
    "    return np.minimum(df['Close'], df['Open']) - df['Low']\n",
    "\n",
    "\n",
    "def get_features(df):\n",
    "    df_feat = df[['Count', 'Open', 'High', 'Low', 'Close', 'Volume', 'VWAP']].copy()\n",
    "    df_feat['Upper_Shadow'] = upper_shadow(df_feat)\n",
    "    df_feat['Lower_Shadow'] = lower_shadow(df_feat)\n",
    "    df_feat['Mean'] = df_feat[['Open', 'High', 'Low', 'Close']].mean(axis=1)\n",
    "    df_feat[\"Median\"] = df_feat[[\"Open\", \"High\", \"Low\", \"Close\"]].median(axis=1)\n",
    "    return df_feat"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "78dc825b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-01-06T14:14:30.622165Z",
     "iopub.status.busy": "2022-01-06T14:14:30.621177Z",
     "iopub.status.idle": "2022-01-06T14:14:34.818309Z",
     "shell.execute_reply": "2022-01-06T14:14:34.819984Z",
     "shell.execute_reply.started": "2022-01-06T12:54:15.530475Z"
    },
    "papermill": {
     "duration": 4.213497,
     "end_time": "2022-01-06T14:14:34.820233",
     "exception": false,
     "start_time": "2022-01-06T14:14:30.606736",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "df_train = df_train[~df_train.isin([np.nan, np.inf, -np.inf]).any(1)].reset_index(drop=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "aaba5fe8",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-01-06T14:14:34.890963Z",
     "iopub.status.busy": "2022-01-06T14:14:34.890136Z",
     "iopub.status.idle": "2022-01-06T14:14:37.870254Z",
     "shell.execute_reply": "2022-01-06T14:14:37.870672Z",
     "shell.execute_reply.started": "2022-01-06T12:54:20.926650Z"
    },
    "papermill": {
     "duration": 3.031141,
     "end_time": "2022-01-06T14:14:37.870818",
     "exception": false,
     "start_time": "2022-01-06T14:14:34.839677",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Memory usage of dataframe is 1545.49 MB\n",
      "Memory usage after optimization is: 515.16 MB\n",
      "Decreased by 66.7%\n"
     ]
    }
   ],
   "source": [
    "def reduce_mem_usage(df):\n",
    "    start_mem = df.memory_usage().sum() / 1024**2\n",
    "    print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))\n",
    "    \n",
    "    for col in df.columns:\n",
    "        col_type = df[col].dtype\n",
    "        \n",
    "        if col_type != object:\n",
    "            c_min = df[col].min()\n",
    "            c_max = df[col].max()\n",
    "            if str(col_type)[:3] == 'int':\n",
    "                if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:\n",
    "                    df[col] = df[col].astype(np.int8)\n",
    "                elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:\n",
    "                    df[col] = df[col].astype(np.int16)\n",
    "                elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:\n",
    "                    df[col] = df[col].astype(np.int32)\n",
    "                elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:\n",
    "                    df[col] = df[col].astype(np.int64)  \n",
    "            else:\n",
    "                if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:\n",
    "                    df[col] = df[col].astype(np.float16)\n",
    "                elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:\n",
    "                    df[col] = df[col].astype(np.float32)\n",
    "                else:\n",
    "                    df[col] = df[col].astype(np.float64)\n",
    "    df[\"Count\"] = df[\"Count\"].astype(np.int16)\n",
    "\n",
    "    end_mem = df.memory_usage().sum() / 1024**2\n",
    "    \n",
    "    print('Memory usage after optimization is: {:.2f} MB'.format(end_mem))\n",
    "    print('Decreased by {:.1f}%'.format(100 * (start_mem - end_mem) / start_mem))\n",
    "     \n",
    "    return df\n",
    "\n",
    "df_train = reduce_mem_usage(df_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "d483c5bc",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-01-06T14:14:37.898191Z",
     "iopub.status.busy": "2022-01-06T14:14:37.897504Z",
     "iopub.status.idle": "2022-01-06T14:14:37.899598Z",
     "shell.execute_reply": "2022-01-06T14:14:37.900089Z",
     "shell.execute_reply.started": "2022-01-06T12:55:18.072448Z"
    },
    "papermill": {
     "duration": 0.017849,
     "end_time": "2022-01-06T14:14:37.900218",
     "exception": false,
     "start_time": "2022-01-06T14:14:37.882369",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "xgb_params = {\n",
    "    'n_estimators':2000,\n",
    "    'max_depth':11,\n",
    "    'learning_rate':0.05,\n",
    "    'subsample':0.9,\n",
    "    'colsample_bytree':0.7,\n",
    "    'missing':-999,\n",
    "    'random_state':2020,\n",
    "    'tree_method':'gpu_hist'\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "39e4b499",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-01-06T14:14:37.925893Z",
     "iopub.status.busy": "2022-01-06T14:14:37.925155Z",
     "iopub.status.idle": "2022-01-06T14:14:37.929666Z",
     "shell.execute_reply": "2022-01-06T14:14:37.930099Z",
     "shell.execute_reply.started": "2022-01-06T12:55:19.115173Z"
    },
    "papermill": {
     "duration": 0.018681,
     "end_time": "2022-01-06T14:14:37.930223",
     "exception": false,
     "start_time": "2022-01-06T14:14:37.911542",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "def get_Xy_and_model_for_asset(df_train, asset_id):\n",
    "    df = df_train[df_train[\"Asset_ID\"] == asset_id]\n",
    "    X = get_features(df)\n",
    "    y = df['Target']\n",
    "    model = xgb.XGBRegressor(**xgb_params)\n",
    "    model.fit(X, y)\n",
    "    return model"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "05ea4ab7",
   "metadata": {},
   "source": [
    "## Training"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "ad10deee",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-01-06T14:14:37.958378Z",
     "iopub.status.busy": "2022-01-06T14:14:37.957856Z",
     "iopub.status.idle": "2022-01-06T14:36:03.307041Z",
     "shell.execute_reply": "2022-01-06T14:36:03.307468Z",
     "shell.execute_reply.started": "2022-01-06T12:55:19.732050Z"
    },
    "papermill": {
     "duration": 1285.366043,
     "end_time": "2022-01-06T14:36:03.307636",
     "exception": false,
     "start_time": "2022-01-06T14:14:37.941593",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training model for Binance Coin     (ID=0 )\n",
      "Training model for Bitcoin          (ID=1 )\n",
      "Training model for Bitcoin Cash     (ID=2 )\n",
      "Training model for Cardano          (ID=3 )\n",
      "Training model for Dogecoin         (ID=4 )\n",
      "Training model for EOS.IO           (ID=5 )\n",
      "Training model for Ethereum         (ID=6 )\n",
      "Training model for Ethereum Classic (ID=7 )\n",
      "Training model for IOTA             (ID=8 )\n",
      "Training model for Litecoin         (ID=9 )\n",
      "Training model for Maker            (ID=10)\n",
      "Training model for Monero           (ID=11)\n",
      "Training model for Stellar          (ID=12)\n",
      "Training model for TRON             (ID=13)\n",
      "CPU times: user 21min 15s, sys: 7.94 s, total: 21min 23s\n",
      "Wall time: 21min 25s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "models = {}\n",
    "\n",
    "for asset_id, asset_name in zip(df_assets['Asset_ID'], df_assets['Asset_Name']):\n",
    "    print(f\"Training model for {asset_name:<16} (ID={asset_id:<2})\")\n",
    "    try:\n",
    "        model = get_Xy_and_model_for_asset(df_train, asset_id)\n",
    "        models[asset_id] = model\n",
    "    except:         \n",
    "        models[asset_id] = None"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d440a3f1",
   "metadata": {},
   "source": [
    "## Kaggle submission"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "d9ed8022",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2022-01-06T14:36:03.345969Z",
     "iopub.status.busy": "2022-01-06T14:36:03.345275Z",
     "iopub.status.idle": "2022-01-06T14:36:03.899185Z",
     "shell.execute_reply": "2022-01-06T14:36:03.899904Z",
     "shell.execute_reply.started": "2022-01-06T13:00:36.954560Z"
    },
    "papermill": {
     "duration": 0.576852,
     "end_time": "2022-01-06T14:36:03.900110",
     "exception": false,
     "start_time": "2022-01-06T14:36:03.323258",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "This version of the API is not optimized and should not be used to estimate the runtime of your code on the hidden test set.\n",
      "CPU times: user 1.04 s, sys: 3.95 ms, total: 1.04 s\n",
      "Wall time: 550 ms\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "env = gresearch_crypto.make_env()\n",
    "iter_test = env.iter_test()\n",
    "\n",
    "\n",
    "for i, (df_test, df_pred) in enumerate(iter_test):\n",
    "    for j , row in df_test.iterrows():\n",
    "        if models[row['Asset_ID']] is not None:\n",
    "            try:\n",
    "                model = models[row['Asset_ID']]\n",
    "                x_test = get_features(pd.DataFrame([row]))\n",
    "                y_pred = model.predict(x_test)[0]\n",
    "                df_pred.loc[df_pred['row_id'] == row['row_id'], 'Target'] = y_pred\n",
    "            except:\n",
    "                df_pred.loc[df_pred['row_id'] == row['row_id'], 'Target'] = 0\n",
    "                traceback.print_exc()\n",
    "        else: \n",
    "            df_pred.loc[df_pred['row_id'] == row['row_id'], 'Target'] = 0\n",
    "    env.predict(df_pred)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4c8cf6c5",
   "metadata": {},
   "source": [
    "## Results with different n_estimators"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f573f59a",
   "metadata": {},
   "source": [
    "* 500 - 0.2126\n",
    "* 1000 - 0.2659\n",
    "* 1500 - 0.3038\n",
    "* 2000 - 0.3362\n",
    "* 3000 - 0.3743\n",
    "* 4000 - 0.4023\n",
    "* 4500 - Ended memory\n",
    "* 5000 - Ended memory"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e5b4500e",
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "x = [500, 1000, 1500, 2000, 3000, 4000]\n",
    "y = [0.2126, 0.2659, 0.3038, 0.3362, 0.3743, 0.4023]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "f108cf44",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(x,y)\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.8"
  },
  "papermill": {
   "default_parameters": {},
   "duration": 1356.100817,
   "end_time": "2022-01-06T14:36:05.164882",
   "environment_variables": {},
   "exception": null,
   "input_path": "__notebook__.ipynb",
   "output_path": "__notebook__.ipynb",
   "parameters": {},
   "start_time": "2022-01-06T14:13:29.064065",
   "version": "2.3.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}